© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59414
    Prev
    Next
    INDEX
    Explanations

    ala, ole, ulen, ool, al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    m
    1.26
    ↵
    1.13
    ﺭ
    1.06
    with
    1.05
    l
    1.04
    며
    1.04
    ل
    1.00
    ке
    0.98
    ﺍ
    0.93
     administrar
    0.89
    POSITIVE LOGITS
    ه
    1.30
     was
    1.15
    า
    1.09
    स
    1.05
    a
    1.00
    া
    1.00
    س
    1.00
    欉
    0.99
    一個
    0.91
     are
    0.90
    Activations Density 0.000%

    No Known Activations